#46 MiMo-V2-Flash
medium
Invalid SVG
- Cost
- $0.020
- Time
- 284.1s
- Tokens
- 65,689 tok
Xiaomi
Release: 2025-12-16
Tested on: 2026-04-11 01:44
xiaomi/mimo-v2-flash::medium
309B total (15B active)MoEOpen source
(medium)
(none)
Summary
MiMo-V2-Flash scores 7.5 on AI BENCHY and ranks #46. It has N/A reliability, a 70.4% pass rate, $0.038 total cost, and 23.36s average response time.
What makes MiMo-V2-Flash unique: It stands out most in Instructions following, where it ranks #1, while Coding is its weakest area at #18. Its total benchmark cost is unusually low for its score range.
Archived model: this model is no longer updated or tested on new tests.
Model facts
Researched on 2026-08-12
- Parameters
- 309B total (15B active)
- Architecture
- MoE
- Availability
- Open source
- License
- MIT
7.5
Consistency
8.6
N/A
$0.038
Total Output Tokens
127,569
Total Input Tokens
0
Input Price
$0.090 / 1M
Output Price
$0.290 / 1M
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-06-04 13:48 New test added | 6.3 | 10.0 | $0.043 ↑ | Compare | |
| 2026-05-22 00:20 Suite changed | 7.1 | 10.0 | $0.038 | Compare | |
| 2026-04-11 01:44 First recorded run | 7.5 | N/A | $0.038 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 7.5 | 8.6 | N/A | 11/18 | 3 | 127,569 | 0 | $0.038 | 23.36s |
| 2026-05-22 00:20 · Suite changed | 60/60 attempts | 7.1 | 8.7 | 10.0 | 11/20 | 3 | 127,609 | 0 | $0.038 | 20.26s |
| Difference | — | +0.4 | -0.1 | 0 | 0 | -40 | 0 | -$0.001 | +3099ms |
Benchmark coverage differs: 54/54 attempts (Target: 3 repeats per test) versus 60/60 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.1 | 7.9 | |
| Coding | 4.7 | 1.6 | |
| Combined | 9.8 | 10.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 5.9 | 7.2 | |
| General Intelligence | 4.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 7.7 | 10.0 | |
| Tool Calling | 10.0 | 10.0 |